Ahmed Elshabrawy


2023

pdf
CamelParser2.0: A State-of-the-Art Dependency Parser for Arabic
Ahmed Elshabrawy | Muhammed AbuOdeh | Go Inoue | Nizar Habash
Proceedings of ArabicNLP 2023

We present CamelParser2.0, an open-source Python-based Arabic dependency parser targeting two popular Arabic dependency formalisms, the Columbia Arabic Treebank (CATiB), and Universal Dependencies (UD). The CamelParser2.0 pipeline handles the processing of raw text and produces tokenization, part-of-speech and rich morphological features. As part of developing CamelParser2.0, we explore many system design hyper-parameters, such as parsing model architecture and pretrained language model selection, achieving new state-of-the-art performance across diverse Arabic genres under gold and predicted tokenization settings.